Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

SHREC 2025: Protein surface shape retrieval including electrostatic potential.

Computers & graphics·2026
Same author

DAQplugin: Deep Learning based Real-time Model Evaluation Plugin for ChimeraX.

bioRxiv : the preprint server for biology·2026
Same author

Direct Detection and Atomic Modeling of Ligands in Cryo-EM Maps Using Deep Learning.

bioRxiv : the preprint server for biology·2026
Same author

snRNA-seq identifies Fmo2<sup>+</sup> fibroblasts as drivers of hyperglycemic memory-induced cardiac injury.

npj metabolic health and disease·2026
Same author

On the state of protein function prediction: a report on the fourth CAFA challenge.

bioRxiv : the preprint server for biology·2026
Same author

PL-PatchSurfer3: improved structure-based virtual screening for structure variation using 3D Zernike descriptors.

Journal of cheminformatics·2026

Related Experiment Video

Updated: Jan 3, 2026

Application of I TASSER, trRosetta, UCSF Chimera, HADDOCK server, and HEX loria for De Novo and In Silico Design of Proteins
05:08

Application of I TASSER, trRosetta, UCSF Chimera, HADDOCK server, and HEX loria for De Novo and In Silico Design of Proteins

Published on: July 8, 2025

866

Protein docking model evaluation by 3D deep convolutional neural networks.

Xiao Wang1, Genki Terashi2, Charles W Christoffer1

  • 1Department of Computer Science, Purdue University, West Lafayette, IN 47907, USA.

Bioinformatics (Oxford, England)
|November 21, 2019
PubMed
Summary
This summary is machine-generated.

We developed DOcking decoy selection with Voxel-based deep neural nEtwork (DOVE), a deep learning method to accurately evaluate protein complex models. DOVE outperforms existing scoring functions in identifying near-native protein docking models.

More Related Videos

Author Spotlight: Streamlining Protein Target Prediction and Validation via Molecular Docking and CETSA
10:21

Author Spotlight: Streamlining Protein Target Prediction and Validation via Molecular Docking and CETSA

Published on: February 23, 2024

3.6K
Incorporating Target Protein Structure Flexibility and Dynamics in Computational Drug Discovery Using Ensemble-Based Docking Analysis
08:49

Incorporating Target Protein Structure Flexibility and Dynamics in Computational Drug Discovery Using Ensemble-Based Docking Analysis

Published on: June 20, 2025

1.0K

Related Experiment Videos

Last Updated: Jan 3, 2026

Application of I TASSER, trRosetta, UCSF Chimera, HADDOCK server, and HEX loria for De Novo and In Silico Design of Proteins
05:08

Application of I TASSER, trRosetta, UCSF Chimera, HADDOCK server, and HEX loria for De Novo and In Silico Design of Proteins

Published on: July 8, 2025

866
Author Spotlight: Streamlining Protein Target Prediction and Validation via Molecular Docking and CETSA
10:21

Author Spotlight: Streamlining Protein Target Prediction and Validation via Molecular Docking and CETSA

Published on: February 23, 2024

3.6K
Incorporating Target Protein Structure Flexibility and Dynamics in Computational Drug Discovery Using Ensemble-Based Docking Analysis
08:49

Incorporating Target Protein Structure Flexibility and Dynamics in Computational Drug Discovery Using Ensemble-Based Docking Analysis

Published on: June 20, 2025

1.0K

Area of Science:

  • Computational Biology
  • Structural Biology
  • Bioinformatics

Background:

  • Protein quaternary structure is crucial for understanding cellular processes.
  • Computational methods aid in predicting protein complex structures.
  • Identifying accurate models from numerous predictions remains a challenge.

Purpose of the Study:

  • To develop a novel computational approach for evaluating protein docking models.
  • To improve the accuracy of identifying near-native protein complex structures.

Main Methods:

  • Developed DOcking decoy selection with Voxel-based deep neural nEtwork (DOVE), a convolutional deep neural network.
  • Utilized 3D voxel scanning of protein-protein interfaces with atomic interaction types and energetic contributions as input features.
  • Trained and validated models on ZDock and DockGround databases.

Main Results:

  • DOVE effectively evaluates protein docking models.
  • The deep learning approach significantly outperformed existing scoring functions.
  • Feature combinations tested demonstrated superior performance.

Conclusions:

  • DOVE provides a powerful new tool for protein complex structure prediction.
  • Deep learning enhances the ability to select accurate protein models.
  • The method offers critical insights into molecular mechanisms of protein complexes.